Each skill is a few short lessons, then practice. You rate yourself at the start and again at the end.
Core to the job
Chapter 2
Directing coding agents
Instruct AI coding tools and spot flaws in their code
What you'll learn
Executable task specs
Repository instruction file
Agent boundaries
Autonomy levels
Parallel runs
Review evidence
Agent failure patterns
Practice
Rewrite the spec an agent got wrong twice35 min
Audit Machine-Written Code That Looks Right but Isn't20 min
Split One Feature Across Three Agent Runs Without Them Colliding30 min
Chapter 2
Prompt engineering
Write prompts that use examples and ask for machine-readable answers
What you'll learn
System and user prompts
Format constraints
Few-shot examples
Prompt versions
Practice
Fix a Flaky Prompt by Adding a Format Constraint15 min
Chapter 4
Programming languages
Build small programs in one language, handling input and errors
What you'll learn
Types and values
Control flow
Error handling
Asynchronous work
Practice
Trace a Function and Predict Its Output10 min
Chapter 4
Reading code
Explain unfamiliar code and predict what a function outputs
What you'll learn
Feature entry point
Call chain
Reference search
Code reading notes
Practice
Read 100 lines of unfamiliar code30 min
Chapter 4
Git
Save clear changes to a project's history and request review
What you'll learn
Change states
Short-lived branches
Merge conflict
Useful commit message
Pull request review
Practice
Untangle a Merge Conflict20 min
Chapter 5
Code quality
Review code for unclear names, then tidy a messy function
What you'll learn
Clear names
Single responsibility
Review the risk
Explain the reason
Proportionate change
Practice
Review Code for Quality Issues15 min
8 more in the plan
AI language modelsMeasure the size of AI requests and compare randomness settingsCh 2
What you'll learn
Tokens and context
Sampling variation
Model trade-offs
Embeddings for search
Practice
Count Tokens and Predict Context Limits15 min
Secure codingFind risks in a login process and remove exposed passwordsCh 5
What you'll learn
Trust boundaries
Access control
Secret handling
Dependency risk
Practice
Spot Security Risks in a Login Flow15 min
DebuggingUse error messages to find bugs and explain your fixesCh 7
What you'll learn
Hypothesis before keyboard
Reliable reproduction
Root cause, not symptom
Narrow it down
Reading a stack trace
Practice
Find the Bug Using an Error Message10 min
Writing testsWrite tests for small functions, including odd and wrong inputsCh 7
What you'll learn
Testing pyramid
Behaviour test
Test isolation
Regression test
Practice
Write Test Cases for a Tip Calculator20 min
Problem solvingTest each possible cause of a problem instead of guessingCh 8
What you'll learn
Problem vs symptom
Clean problem splits
Root cause
Deciding under uncertainty
Practice
Separate the Problem from the Symptom10 min
Critical thinkingSpot a weak assumption and ask where numbers come fromCh 8
What you'll learn
The hidden assumption
Argue the other side
The base rate
Fact vs inference
Wanting it to be true
Practice
Spot the Weak Link in an Argument10 min
CommunicationRewrite an update for two different readers, cutting extra linesCh 9
What you'll learn
Lead with the point
Match detail to the reader
Said versus heard
Specific feedback
Practice
Rewrite the Same Update for Two Different Readers20 min
Adapting to changeTry a new tool and describe how you handled changeCh 9
What you'll learn
Change vs your response
The messy in-between
Not there yet
Real change vs a feeling
Your plan
Chapter by chapter.
13 chapters, in this order. Chapter 1 is free.
1~2 wks
See the work of an AI coding agent operator
StartFree
2~2 wks
Get working code from AI agents
Skills
3~2 wks
Write up a system you built
Project
4~2 wks
Read, write and track code with Git
Skills
5~2 wks
Catch quality and security problems in code
Skills
61–2 wks
Talk to two working coding agent operators
People
7~2 wks
Test code and find bugs fast
Skills
8~2 wks
Find the cause before you fix it
Skills
9~2 wks
Explain your work clearly as things change
Skills
10~2 wks
Capstone: ship a feature by directing coding agents
Project
111–2 wks
Answer the questions interviewers ask
Interview
121–2 wks
Decide how you will get in
Decide
13on your timeline
Send your first applications
Apply
The job
What a AI Coding Agent Operator does
Runs many AI coding agents (software that writes and edits code on its own, such as Devin, Cursor, or Claude Code) at the same time. Writes clear task notes, checks the code the agents return, fixes what they miss, and merges working changes into the product.
The work
Write clear task specs that AI coding agents can turn into code
Start and watch several agent runs across many tickets at once
Review agent-written code and catch bugs the agent missed
Test changes locally, then merge safe code into the project
Break large tickets into small steps an agent can finish
Steer a stuck agent with hints, examples, and tighter limits
Track which agents do well on which kinds of work
A typical day
Scan the ticket queue and pick work to hand to agents
Write task specs, then launch a few agent runs in parallel
Switch between runs, reading code and giving each agent feedback
Pull a finished branch, run tests, and check for hidden bugs
Fix small gaps by hand, then open and merge a pull request
Note what worked, update prompts, and share progress with the team
Tools
AI coding agents and assistants: Devin, Claude Code, Cursor, GitHub CopilotProgramming languages: Python, JavaScript, TypeScript, GoVersion control: Git, GitHubIssue tracking: Jira, Linear, GitHub IssuesTesting: Pytest, Jest, PlaywrightContainers and CI: Docker, GitHub ActionsCode review: pull requests, diff viewers
Ways in
There is more than one route.
Ways to study
Bachelor degree in computer science or software engineering
Diploma or certificate in programming with strong project work
Coding bootcamp focused on web or backend development
Self-study with online courses plus a real, shipped portfolio
Apprenticeship or trainee role with mentored coding and review work
How people get their first job
Learn one language well and ship 2 to 4 small projects
Practice driving AI coding agents on your own real tickets
Build a habit of careful code review on open source pull requests
Start as a junior developer and take on agent-assisted tasks
Contribute small fixes to open source to learn team workflows
How long does it take to become a ai coding agent operator with Welica?
The plan is 13 chapters, 5–6 months at 15 to 30 minutes a day. You can go faster or slower; the plan moves with you.
Do I need a degree?
Not always. Common routes are bachelor degree in computer science or software engineering, diploma or certificate in programming with strong project work, coding bootcamp focused on web or backend development, self-study with online courses plus a real, shipped portfolio, or apprenticeship or trainee role with mentored coding and review work.
What is free?
Chapter 1, See the work of an AI coding agent operator, is free for good. Premium unlocks the rest of the plan.